Index: lib/Transforms/IPO/PassManagerBuilder.cpp
===================================================================
--- lib/Transforms/IPO/PassManagerBuilder.cpp
+++ lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -241,12 +241,18 @@
     MPM.add(createInstructionCombiningPass()); // Combine silly seq's
     return;
   }
+
+  // This starts the main loop pass pipeline. It is critically important to not
+  // introduce non-loop passes into the middle of this. We want to re-run the
+  // entire pipeline on outer loops after the pipeline simplifies inner loops.
+  // Without this, significant phase ordering problems can develop.
+
   // Rotate Loop - disable header duplication at -Oz
   MPM.add(createLoopRotatePass(SizeLevel == 2 ? 0 : -1));
   MPM.add(createLICMPass());                  // Hoist loop invariants
   MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3));
-  MPM.add(createCFGSimplificationPass());
-  MPM.add(createInstructionCombiningPass());
+  MPM.add(createLoopSimplifyCFGPass());
+  MPM.add(createLoopInstSimplifyPass());
   MPM.add(createIndVarSimplifyPass());        // Canonicalize indvars
   MPM.add(createLoopIdiomPass());             // Recognize idioms like memset.
   MPM.add(createLoopDeletionPass());          // Delete dead loops
@@ -258,6 +264,12 @@
     MPM.add(createSimpleLoopUnrollPass());    // Unroll small loops
   addExtensionsToPM(EP_LoopOptimizerEnd, MPM);
 
+  // Now we are done with the main loop pass pipeline.
+
+  // Clean up the function body from any stuff produced by the loop passes.
+  MPM.add(createCFGSimplificationPass());
+  MPM.add(createInstructionCombiningPass());
+
   if (OptLevel > 1) {
     if (EnableMLSM)
       MPM.add(createMergedLoadStoreMotionPass()); // Merge ld/st in diamonds
Index: test/Analysis/GlobalsModRef/memset-escape.ll
===================================================================
--- test/Analysis/GlobalsModRef/memset-escape.ll
+++ test/Analysis/GlobalsModRef/memset-escape.ll
@@ -17,44 +17,18 @@
 ; CHECK: br i1
 
 define i32 @main() {
-entry:
-  %retval = alloca i32, align 4
-  %c = alloca [1 x i32], align 4
-  store i32 0, i32* %retval, align 4
-  %0 = bitcast [1 x i32]* %c to i8*
-  call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 4, i32 4, i1 false)
-  store i32 1, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 2), align 4
-  store i32 0, i32* @b, align 4
-  br label %for.cond
-
-for.cond:                                         ; preds = %for.inc, %entry
-  %1 = load i32, i32* @b, align 4
-  %cmp = icmp slt i32 %1, 3
-  br i1 %cmp, label %for.body, label %for.end
-
-for.body:                                         ; preds = %for.cond
-  %2 = load i32, i32* @b, align 4
-  %idxprom = sext i32 %2 to i64
-  %arrayidx = getelementptr inbounds [3 x i32], [3 x i32]* @a, i64 0, i64 %idxprom
-  store i32 0, i32* %arrayidx, align 4
-  br label %for.inc
-
-for.inc:                                          ; preds = %for.body
-  %3 = load i32, i32* @b, align 4
-  %inc = add nsw i32 %3, 1
-  store i32 %inc, i32* @b, align 4
-  br label %for.cond
-
-for.end:                                          ; preds = %for.cond
-  %4 = load i32, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 2), align 4
-  %cmp1 = icmp ne i32 %4, 0
-  br i1 %cmp1, label %if.then, label %if.end
-
-if.then:                                          ; preds = %for.end
-  call void @abort() #3
+for.end:
+  call void @llvm.memset.p0i8.i64(i8* bitcast ([3 x i32]* @a to i8*), i8 0, i64 12, i32 4, i1 false)
+  store i32 3, i32* @b, align 4
+  %0 = load i32, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 2), align 4
+  %cmp1 = icmp eq i32 %0, 0
+  br i1 %cmp1, label %if.end, label %if.then
+
+if.then:
+  call void @abort()
   unreachable
 
-if.end:                                           ; preds = %for.end
+if.end:
   ret i32 0
 }
 
Index: test/Other/pass-pipelines.ll
===================================================================
--- test/Other/pass-pipelines.ll
+++ test/Other/pass-pipelines.ll
@@ -36,19 +36,11 @@
 ; should contain the main loop pass pipeline as well.
 ; CHECK-O2-NEXT: FunctionPass Manager
 ; CHECK-O2-NOT: Manager
-; CHECK-O2: Loop Pass Manager
-; CHECK-O2-NOT: Manager
-; FIXME: We shouldn't be pulling out to simplify-cfg and instcombine and
-; causing new loop pass managers.
-; CHECK-O2: Simplify the CFG
-; CHECK-O2-NOT: Manager
-; CHECK-O2: Combine redundant instructions
-; CHECK-O2-NOT: Manager
+; Now the main loop pass pipeline.
 ; CHECK-O2: Loop Pass Manager
 ; CHECK-O2-NOT: Manager
 ; FIXME: It isn't clear that we need yet another loop pass pipeline
 ; and run of LICM here.
-; CHECK-O2-NOT: Manager
 ; CHECK-O2: Loop Pass Manager
 ; CHECK-O2-NEXT: Loop Invariant Code Motion
 ; CHECK-O2-NOT: Manager